Gabriele Sarti
Avatar

Gabriele Sarti

PhD in Natural Language Processing

CLCG, University of Groningen

About me

Welcome to my website! 👋 I am a PhD student at the Natural Language Processing group (GroNLP 🐮) & the InCLoW research team at the University of Groningen. I’m also a member of the InDeep consortium, working on user-centric interpretability for multilingual generation and machine translation. My supervisors are Arianna Bisazza, Malvina Nissim and Grzegorz Chrupała.

Previously, I was a research intern at Amazon Translate NYC, a research scientist at Aindo, a Data Science MSc student at the University of Trieste and a co-founder of the AI Student Society.

My research focuses on interpretability for generative language models, with a particular interest on operationalizing advances in model understanding for the benefit of users. For this reason, I lead the development of robust open-source interpretability software to enable reproducible analyses of model behaviors. I am also excited about human-computer interaction, and in particular how human behavioral signals can improve human-AI collaboration.

Your (anonymous) constructive feedback is always welcome! 🙂

Interests

  • Conditional Language Generation
  • Deep Learning Interpretability
  • Human-AI Collaboration
  • Uncertainty Estimation

Education

Experience

🗞️ News

 

  • PECoRe is accepted to ICLR 2024, and I presented it in Vienna! 🎉 I also co-organized the first Mechanistic Interpretability social at ICLR togehter with Nikhil Prakash, and we had more than 100 attendees!

Selected Publications

 

Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement

We evaluate unsupervised word-level quality estimation (WQE) methods for machine translation, focusing on their robustness to human …
Published in: Arxiv
PDF Code Dataset ArXiv

Steering Large Language Models for Machine Translation Personalization

We evaluate prompting and steering based methods for machine translation personalization in the literary domain.
Published in: Arxiv
PDF ArXiv

QE4PE: Word-level Quality Estimation for Human Post-Editing

We investigate the impact of word-level quality estimation on MT post-editing with 42 professional post-editors.
Published in: Arxiv Preprint
Gabriele Sarti, Vilém Zouhar, Grzegorz Chrupała, Ana Guerberof Arenas, Malvina Nissim, Arianna Bisazza
PDF Code Dataset Paper ArXiv GroTE Demo

Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses

We evaluate the rebus-solving capabilities of large language models on a new Italian dataset.
Published in: CLiC-it 2024
PDF Dataset Paper CALAMITA Challenge Models & Dataset Repository Demo

Multi-property Steering of Large Language Models with Dynamic Activation Composition

We propose Dynamic Activation Composition, an adaptive approach for multi-property activation steering of LLMs
Published in: BlackboxNLP 2024
PDF ArXiv Repository

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation

MIRAGE uses model internals for faithful answer attribution in retrieval-augmented generation applications.
Published in: EMNLP 2024 * Equal contribution
PDF Project ArXiv Demo Repository
See all publications

Blog posts

 

ICLR 2020 Trends: Better & Faster Transformers for Natural Language Processing

A summary of promising directions from ICLR 2020 for better and faster pretrained tranformers language models.
May 3, 2020 14 min read

Recent & Upcoming Talks

Interpreting Latent Features in Large Language Models
May 22, 2025 Room 1313.0344, Harmonie Building, University of Groningen Paper Presentation at InCLoW Reading Group
QE4PE: Word-level Quality Estimation for Human Post-Editing
Apr 15, 2025 Online Invited Talk at DFKI Saarbrücken
Interpretability for Language Models: Current Trends and Applications
Mar 24, 2025 Bernoulli Institute, Faculty of Science and Engineering, University of Groningen Seminar, MSc Course on Trustworthy and Explainable AI, University of Groningen
See all talks

Projects

 

Attributing Context Usage in Language Models

An interpretability framework to detect and attribute context usage in language models’ generations

Inseq: An Interpretability Toolkit for Sequence Generation Models

An open-source library to democratize access to model interpretability for sequence generation models

Contrastive Image-Text Pretraining for Italian

The first CLIP model pretrained on the Italian language.

Covid-19 Semantic Browser

A semantic browser for SARS-CoV-2 and COVID-19 powered by neural language models.

AItalo Svevo: Letters from an Artificial Intelligence

Generating letters with a neural language model in the style of Italo Svevo, a famous italian writer of the 20th century.

Histopathologic Cancer Detection with Neural Networks

A journey into the state of the art of histopathologic cancer detection approaches.